© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31320
    Prev
    Next
    INDEX
    Explanations

    eligible for services

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects occurrences of words related to eligibility (e.g., “eligible” or its variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    不想
    -0.99
    Segu
    -0.93
     accommodating
    -0.92
     невозможно
    -0.92
    คง
    -0.91
    உ
    -0.89
     variedade
    -0.89
    ⧠
    -0.88
     perfecting
    -0.87
    xa
    -0.87
    POSITIVE LOGITS
     to
    2.20
     for
    2.09
     receive
    1.35
     recieve
    1.00
     menerima
    0.99
    According
    0.98
     receives
    0.97
     TRENDS
    0.96
    toluene
    0.96
    RECEIVE
    0.95
    Activations Density 0.021%

    No Known Activations